cool-seq-tool 0.11.0__tar.gz → 0.12.1__tar.gz

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: cool_seq_tool
-Version: 0.11.0
+Version: 0.12.1
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/docs/source/install.rst

@@ -40,11 +40,11 @@ Cool-Seq-Tool requires an available instance of the Universal Transcript Archive
    createuser -U postgres anonymous
    createdb -U postgres -O uta_admin uta
 
-   export UTA_VERSION=uta_20210129b.pgd.gz  # most recent as of 2023/12/05
+   export UTA_VERSION=uta_20241220.pgd.gz  # most recent as of 2025/03/10
    curl -O https://dl.biocommons.org/uta/$UTA_VERSION
    gzip -cdq ${UTA_VERSION} | psql -h localhost -U uta_admin --echo-errors --single-transaction -v ON_ERROR_STOP=1 -d uta -p 5432
 
-By default, Cool-Seq-Tool expects to connect to the UTA database via a PostgreSQL connection served local on port 5432, under the PostgreSQL username ``uta_admin`` and the schema ``uta_20210129b``.
+By default, Cool-Seq-Tool expects to connect to the UTA database via a PostgreSQL connection served local on port 5432, under the PostgreSQL username ``uta_admin`` and the schema ``uta_20241220``.
 
 Set up SeqRepo
 --------------
@@ -56,20 +56,20 @@ Cool-Seq-Tool requires access to `SeqRepo <https://github.com/biocommons/biocomm
 .. code-block::
 
    pip install seqrepo
-   export SEQREPO_VERSION=2024-02-20
+   export SEQREPO_VERSION=2024-12-20
    sudo mkdir /usr/local/share/seqrepo
    sudo chown $USER /usr/local/share/seqrepo
    seqrepo pull -i $SEQREPO_VERSION
 
 .. note::
 
-   Our lab typically uses the latest SeqRepo release, which is ``2024-02-20`` as of this commit. To check for the presence of newer snapshots, use the ``seqrepo list-remote-instances`` CLI command.
+   Our lab typically uses the latest SeqRepo release, which is ``2024-12-20`` as of this commit. To check for the presence of newer snapshots, use the ``seqrepo list-remote-instances`` CLI command.
 
 While this should no longer occur with the latest SeqRepo release, some users in the past have reported experiencing the following error:
 
 .. code-block::
 
-   PermissionError: [Error 13] Permission denied: '/usr/local/share/seqrepo/2024-02-20._fkuefgd' -> '/usr/local/share/seqrepo/2021-01-29'
+   PermissionError: [Error 13] Permission denied: '/usr/local/share/seqrepo/2024-12-20._fkuefgd' -> '/usr/local/share/seqrepo/2024-12-20'
 
 Try moving data manually with ``sudo``:
 

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/docs/source/usage.rst

@@ -80,7 +80,7 @@ Individual classes will accept arguments upon initialization to set parameters r
    * - ``SEQREPO_ROOT_DIR``
      - Path to SeqRepo directory (i.e. contains ``aliases.sqlite3`` database file, and ``sequences`` directory). Used by :py:class:`SeqRepoAccess <cool_seq_tool.handlers.seqrepo_access.SeqRepoAccess>`. If not defined, defaults to ``/usr/local/share/seqrepo/latest``.
    * - ``UTA_DB_URL``
-     - A `libpq connection string <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING>`_, i.e. of the form ``postgresql://<user>:<password>@<host>:<port>/<database>/<schema>``, used by the :py:class:`UtaDatabase <cool_seq_tool.sources.uta_database.UtaDatabase>` class. By default, it is set to ``postgresql://uta_admin:uta@localhost:5432/uta/uta_20210129b``.
+     - A `libpq connection string <https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING>`_, i.e. of the form ``postgresql://<user>:<password>@<host>:<port>/<database>/<schema>``, used by the :py:class:`UtaDatabase <cool_seq_tool.sources.uta_database.UtaDatabase>` class. By default, it is set to ``postgresql://uta_admin:uta@localhost:5432/uta/uta_20241220``.
    * - ``LIFTOVER_CHAIN_37_TO_38``
      - A path to a `chainfile <https://genome.ucsc.edu/goldenPath/help/chain.html>`_ for lifting from GRCh37 to GRCh38. Used by the :py:class:`LiftOver <cool_seq_tool.mappers.liftover.LiftOver>` class as input to `agct <https://pypi.org/project/agct/>`_. If not provided, agct will fetch it automatically from UCSC.
    * - ``LIFTOVER_CHAIN_38_TO_37``

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/src/cool_seq_tool/schemas.py

@@ -43,11 +43,18 @@ class Assembly(str, Enum):
         return [item.value for item in cls]
 
 
+class ManeStatus(str, Enum):
+    """Define constraints for mane status"""
+
+    SELECT = "mane_select"
+    PLUS_CLINICAL = "mane_plus_clinical"
+
+
 class TranscriptPriority(str, Enum):
     """Create Enum for Transcript Priority labels"""
 
-    MANE_SELECT = "mane_select"
-    MANE_PLUS_CLINICAL = "mane_plus_clinical"
+    MANE_SELECT = ManeStatus.SELECT.value
+    MANE_PLUS_CLINICAL = ManeStatus.PLUS_CLINICAL.value
     LONGEST_COMPATIBLE_REMAINING = "longest_compatible_remaining"
     GRCH38 = "grch38"
 
@@ -137,6 +144,7 @@ class ManeGeneData(BaseModel, extra="forbid"):
     ncbi_gene_id: StrictInt
     hgnc_id: StrictInt | None
     symbol: StrictStr
+    status: list[ManeStatus]
 
 
 class ServiceMeta(BaseModelForbidExtra):

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/src/cool_seq_tool/sources/mane_transcript_mappings.py

@@ -117,26 +117,58 @@ class ManeTranscriptMappings:
         :param end: Genomic end position. Assumes residue coordinates.
         :return: Unique MANE gene(s) found for a genomic location
         """
+        # Only interested in rows where genomic location lives
         mane_rows = self.df.filter(
             (start >= pl.col("chr_start"))
             & (end <= pl.col("chr_end"))
             & (pl.col("GRCh38_chr") == ac)
-        ).unique(subset=["#NCBI_GeneID"])
+        )
 
-        if len(mane_rows) == 0:
+        if mane_rows.is_empty():
             return []
 
-        mane_rows = mane_rows.with_columns(
-            pl.col("#NCBI_GeneID")
-            .str.split_exact(":", 1)
-            .struct.field("field_1")
-            .cast(pl.Int32)
-            .alias("ncbi_gene_id"),
-            pl.col("HGNC_ID")
-            .str.split_exact(":", 1)
-            .struct.field("field_1")
-            .cast(pl.Int32)
-            .alias("hgnc_id"),
+        # Group rows by NCBI ID, transform values to representation we want, MANE status
+        # will be converted to list with DESC order
+        mane_rows = mane_rows.group_by("#NCBI_GeneID").agg(
+            [
+                pl.col("#NCBI_GeneID")
+                .first()
+                .str.split_exact(":", 1)
+                .struct.field("field_1")
+                .cast(pl.Int32)
+                .alias("ncbi_gene_id"),
+                pl.col("HGNC_ID")
+                .first()
+                .str.split_exact(":", 1)
+                .struct.field("field_1")
+                .cast(pl.Int32)
+                .alias("hgnc_id"),
+                pl.col("MANE_status")
+                .unique()
+                .str.to_lowercase()
+                .str.replace_all(" ", "_")
+                .alias("status")
+                .sort(descending=True),
+                pl.col("symbol").first(),
+            ]
+        )
+
+        # Sort final rows based on MANE status
+        # First by length (which means gene has both select and plus clinical)
+        # Then by DESC order
+        # Then by NCBI ID ASC order
+        mane_rows = (
+            mane_rows.with_columns(
+                [
+                    pl.col("status").list.len().alias("status_count"),
+                    pl.col("status").list.join("_").alias("status_str"),
+                    pl.col("ncbi_gene_id"),
+                ]
+            )
+            .sort(
+                ["status_count", "status_str", "ncbi_gene_id"],
+                descending=[True, True, False],
+            )
+            .drop(["status_count", "status_str", "#NCBI_GeneID"])
         )
-        mane_rows = mane_rows.select(["ncbi_gene_id", "hgnc_id", "symbol"])
         return [ManeGeneData(**mane_gene) for mane_gene in mane_rows.to_dicts()]

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/src/cool_seq_tool/sources/uta_database.py

@@ -27,7 +27,7 @@ from cool_seq_tool.schemas import (
 UTADatabaseType = TypeVar("UTADatabaseType", bound="UtaDatabase")
 
 UTA_DB_URL = environ.get(
-    "UTA_DB_URL", "postgresql://uta_admin:uta@localhost:5432/uta/uta_20210129b"
+    "UTA_DB_URL", "postgresql://uta_admin:uta@localhost:5432/uta/uta_20241220"
 )
 
 _logger = logging.getLogger(__name__)

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/src/cool_seq_tool.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: cool_seq_tool
-Version: 0.11.0
+Version: 0.12.1
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/tests/conftest.py

@@ -340,10 +340,19 @@ def genomic_tx_data():
 @pytest.fixture(scope="session")
 def egfr_mane_gene():
     """Create test fixture for EGFR MANE gene"""
-    return ManeGeneData(ncbi_gene_id=1956, hgnc_id=3236, symbol="EGFR")
+    return ManeGeneData(
+        ncbi_gene_id=1956, hgnc_id=3236, symbol="EGFR", status=["mane_select"]
+    )
 
 
 @pytest.fixture(scope="session")
-def braf_mane_gene():
+def braf_mane_genes():
     """Create test fixture for BRAF MANE gene"""
-    return ManeGeneData(ncbi_gene_id=673, hgnc_id=1097, symbol="BRAF")
+    return [
+        ManeGeneData(
+            ncbi_gene_id=673,
+            hgnc_id=1097,
+            symbol="BRAF",
+            status=["mane_select", "mane_plus_clinical"],
+        ),
+    ]

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/tests/mappers/test_mane_transcript.py

@@ -143,13 +143,13 @@ def grch38_egfr(egfr_mane_gene):
 
 
 @pytest.fixture(scope="module")
-def grch38_braf(braf_mane_gene):
+def grch38_braf(braf_mane_genes):
     """Create a test fixture for grch38 responses BRAF V600E (genomic)."""
     params = {
         "pos": (140753335, 140753336),
         "status": TranscriptPriority.GRCH38.value,
         "ac": "NC_000007.14",
-        "mane_genes": [braf_mane_gene],
+        "mane_genes": braf_mane_genes,
     }
     return GenomicRepresentation(**params)
 

{cool_seq_tool-0.11.0 → cool_seq_tool-0.12.1}/tests/sources/test_mane_transcript_mappings.py

@@ -209,28 +209,75 @@ def test_get_mane_data_from_chr_pos(
 
 
 def test_get_genomic_mane_genes(
-    test_mane_transcript_mappings, braf_mane_gene, egfr_mane_gene
+    test_mane_transcript_mappings, braf_mane_genes, egfr_mane_gene
 ):
     """Test that get_genomic_mane_genes method works correctly"""
     new_df = pl.DataFrame(
         {
-            "#NCBI_GeneID": ["GeneID:673", "GeneID:673", "GeneID:1956", "GeneID:1"],
+            "#NCBI_GeneID": [
+                "GeneID:673",
+                "GeneID:673",
+                "GeneID:1956",
+                "GeneID:1",
+                "GeneID:2",
+                "GeneID:2",
+                "GeneID:3",
+            ],
             "Ensembl_Gene": [
                 "ENSG00000157764.14",
                 "ENSG00000157764.14",
                 "ENSG00000146648.21",
                 "ENSG1.1",
+                "ENSG1.1",
+                "ENSG1.1",
+                "ENSG1.1",
+            ],
+            "HGNC_ID": [
+                "HGNC:1097",
+                "HGNC:1097",
+                "HGNC:3236",
+                "HGNC:1",
+                "HGNC:2",
+                "HGNC:2",
+                "HGNC:3",
             ],
-            "HGNC_ID": ["HGNC:1097", "HGNC:1097", "HGNC:3236", "HGNC:2"],
-            "symbol": ["BRAF", "BRAF", "EGFR", "Dummy"],
+            "symbol": ["BRAF", "BRAF", "EGFR", "Dummy1", "Dummy2", "Dummy2", "Dummy3"],
             "GRCh38_chr": [
                 "NC_000007.14",
                 "NC_000007.14",
                 "NC_000007.14",
                 "NC_000007.14",
+                "NC_000007.14",
+                "NC_000007.14",
+                "NC_000007.14",
+            ],
+            "chr_start": [
+                140719337,
+                140730665,
+                55019017,
+                55019017,
+                55019017,
+                55019017,
+                55019017,
+            ],
+            "chr_end": [
+                140924929,
+                140924929,
+                55211628,
+                55211628,
+                55211628,
+                55211628,
+                55211628,
+            ],
+            "MANE_status": [
+                "MANE Plus Clinical",
+                "MANE Select",
+                "MANE Select",
+                "MANE Plus Clinical",
+                "MANE Select",
+                "MANE Plus Clinical",
+                "MANE Select",
             ],
-            "chr_start": [140719337, 140730665, 55019017, 55019017],
-            "chr_end": [140924929, 140924929, 55211628, 55211628],
         }
     )
 
@@ -238,14 +285,29 @@ def test_get_genomic_mane_genes(
         mane_genes = test_mane_transcript_mappings.get_genomic_mane_genes(
             "NC_000007.14", 140753336, 140753336
         )
-        assert mane_genes == [braf_mane_gene]
+        assert mane_genes == braf_mane_genes
 
         mane_genes = test_mane_transcript_mappings.get_genomic_mane_genes(
             "NC_000007.14", 55191822, 55191822
         )
-        assert len(mane_genes) == 2
-        assert egfr_mane_gene in mane_genes
-        assert ManeGeneData(ncbi_gene_id=1, hgnc_id=2, symbol="Dummy") in mane_genes
+        assert mane_genes == [
+            ManeGeneData(
+                ncbi_gene_id=2,
+                hgnc_id=2,
+                symbol="Dummy2",
+                status=["mane_select", "mane_plus_clinical"],
+            ),
+            ManeGeneData(
+                ncbi_gene_id=3, hgnc_id=3, symbol="Dummy3", status=["mane_select"]
+            ),
+            egfr_mane_gene,
+            ManeGeneData(
+                ncbi_gene_id=1,
+                hgnc_id=1,
+                symbol="Dummy1",
+                status=["mane_plus_clinical"],
+            ),
+        ]
 
         # No MANE genes found for given genomic location
         mane_genes = test_mane_transcript_mappings.get_genomic_mane_genes(